Title :
Reinforcement learning-based output feedback control of nonlinear systems with input constraints
Author :
He, P. ; Jagannathan, S.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Missouri, Rolla, MO, USA
Abstract :
A novel neural network (NN)-based output feedback controller with magnitude constraints is designed to deliver a desired tracking performance for a class of multi-input and multi-output (MIMO) strict feedback nonlinear discrete-time systems. Reinforcement learning is proposed for the output feedback controller, which uses three NNs: 1) an NN observer to estimate the system states with the input-output data, 2) a critic NN to approximate certain strategic utility function, and 3) an action NN to minimize both the strategic utility function and the unknown dynamics estimation errors. Using the Lyapunov approach, the uniformly ultimate boundedness (UUB) of the state estimation errors, the tracking errors and weight estimates is shown.
Keywords :
discrete time systems; feedback; learning (artificial intelligence); neural nets; nonlinear systems; Lyapunov approach; MIMO; magnitude constraints; multiinput-multioutput; neural network; nonlinear discrete-time systems; output feedback control; reinforcement learning; state estimation error; tracking error; Control systems; Learning; MIMO; Neural networks; Neurofeedback; Nonlinear control systems; Nonlinear systems; Observers; Output feedback; State estimation; Neural networks (NNs); output feedback control; reinforcement learning; Algorithms; Artificial Intelligence; Computer Simulation; Feedback; Models, Theoretical; Neural Networks (Computer); Nonlinear Dynamics; Signal Processing, Computer-Assisted;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2004.840124
